Transformers

You are viewing v5.8.0 version. A newer version v5.8.1 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Open WebUI

Open WebUI provides a self-hosted interface for offline models. Enable CORS to serve local models (it’s disabled by default for security).

transformers serve --enable-cors

To use the server for speech-to-text, go to Settings > Audio.

Set Speech-to-Text Engine to OpenAI.
Set the URL to http://localhost:8000/v1.
Enter a transcription model in SST Model (openai/whisper-large-v3). Find more models on the Hub.

Start a chat and speak. The model transcribes your audio into the input field.